Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0903. Min Range: -8.0903
Max Act: 8.0903. Min Act: -0.1700
Data Index: 7201497 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0903. Min Range: -8.0903
Max Act: 8.0903. Min Act: -0.1700
Data Index: 6174987 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.9965. Min Act: -0.1700
Data Index: 6342690 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.8403. Min Act: -0.1700
Data Index: 6576628 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.7153. Min Act: -0.1700
Data Index: 4485159 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.5903. Min Act: -0.1700
Data Index: 5872356 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.6215. Min Act: -0.1700
Data Index: 7552433 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.5903. Min Act: -0.1700
Data Index: 5230300 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.4340. Min Act: -0.1700
Data Index: 2229288 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.4028. Min Act: -0.1700
Data Index: 1181088 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.4340. Min Act: -0.1700
Data Index: 8639920 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.3403. Min Act: -0.1700
Data Index: 3865410 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.3403. Min Act: -0.1700
Data Index: 3642706 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.4028. Min Act: -0.1700
Data Index: 2975524 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.3403. Min Act: -0.1700
Data Index: 180771 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.3403. Min Act: -0.1700
Data Index: 4703250 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.2778. Min Act: -0.1700
Data Index: 1242911 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.3090. Min Act: -0.1700
Data Index: 5564570 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.3403. Min Act: -0.1700
Data Index: 5377182 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0903. Min Range: -8.0903
Max Act: 7.2153. Min Act: -0.1700
Data Index: 7478991 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19